INDEX

Explanations

variations of the word "bridge."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ozy

-0.18

 Beled

-0.17

LOY

-0.16

macen

-0.16

hole

-0.15

è´£

-0.15

ÑĨÐ¸Ð½

-0.14

 bullet

-0.14

yy

-0.14

.scalablytyped

-0.14

POSITIVE LOGITS

gewater

0.26

ging

0.22

gend

0.20

git

0.17

ocus

0.17

port

0.17

ema

0.17

get

0.17

bane

0.17

ged

0.17

Activations Density 0.009%

variations of the word "bridge."

No Comments

No Known Activations